{"id":"W4306679461","doi":"10.1609/aiide.v18i1.21958","title":"Automated Play-Testing through RL Based Human-Like Play-Styles Generation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Variety (cybernetics); Video game; Reinforcement learning; Human–computer interaction; Production (economics); Order (exchange); Learning styles; Game design; Artificial intelligence; Multimedia; Psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000357731,0.0003891068,0.0003496133,0.0001879771,0.0008102629,0.0009239943,0.001599764,0.00006393458,0.0001221628],"category_scores_gemma":[0.0003210097,0.0003265597,0.0001629379,0.0005910253,0.0003194089,0.001705521,0.001108474,0.0004731974,0.0000312615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002514542,"about_ca_system_score_gemma":0.0001007024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008351015,"about_ca_topic_score_gemma":0.000008601774,"domain_scores_codex":[0.9969567,0.00005082881,0.0008625251,0.0008225271,0.0008360966,0.0004713201],"domain_scores_gemma":[0.9981396,0.0002409453,0.0006605968,0.0003380124,0.0005193769,0.000101446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002925748,0.00181267,0.001854,0.00006496368,0.0001558974,0.00001038534,0.01314184,0.004590512,0.2232526,0.6425723,0.001669749,0.1105825],"study_design_scores_gemma":[0.00005643645,0.001076496,0.0001383309,0.0001746416,0.00001628404,0.00001619482,0.005074464,0.4857894,0.4873936,0.01925434,0.0005878315,0.0004219195],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9308264,0.00003686116,0.04325331,0.002872152,0.001099061,0.00125535,0.00007004257,0.0004920359,0.02009483],"genre_scores_gemma":[0.9976612,0.000005304432,0.001118134,0.0007227917,0.00006911418,0.0001570521,0.000009558661,0.00002398438,0.0002329074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.623318,"threshold_uncertainty_score":0.9999186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09833239966406118,"score_gpt":0.3164450125912762,"score_spread":0.218112612927215,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}